Machine Learning Model Development GUIs

Machine Learning regression

Optimization and Cross-validation v1.0

Machine Learning classification

Divide Dataset and Develop Models

Data set Balancer

Activity Landscape Plot

The latest version of Python and the dependencies (as given below) should have been installed into the system. The presented GUIs use the scikit-learn and other libraries for hyperparameter optimization and machine learning regression model development (presently Random Forest regression, AdaBoost, Gradient Boost and Extreme Gradient Boost regression, Support Vector Machine and Linear SVM regression and Ridge regression) and machine learning classification model development (presently linear discriminant analysis, logistic regression, support vector classification, and random forest classification).

Machine Learning regression

Dependencies Installer

Hyperparameter Optimizer v1.2

(Uploaded on April 07, 2023)

Hyperparameter Optimizer V1.0 (Uploaded on March 09, 2023)

Optimization and Cross-validation v1.0

Uploaded on May 05, 2023

Manual_Optimization.pdf

Machine Learning Regressor v 2.1

(Uploaded on June 25, 2023)

It computes additional validation metrics.

Machine Learning Regressor v 2.0

(Uploaded on April 10, 2023)

It includes the Feature selection option.

Machine Learning Regressor v1.0 (Uploaded on March 09, 2023)

Manual.pdf

Presently all tools are restricted.

The manual is available here.

TO USE THE TOOLS, PLEASE SIGN THE NEW LICENSE AGREEMENT FORM (DATED 15 FEBRUARY 2023) AND SEND IT TO THE EMAIL ADDRESS GIVEN AT THE BOTTOM OF THIS PAGE. The Licensee will also fill in the form https://forms.gle/1r3TTy7RmZCQvqBt5

Reference: Arkaprava Banerjee, Supratik Kar, Souvik Pore & Kunal Roy (2023) Efficient predictions of cytotoxicity of TiO2-based multi-component nanoparticles using a machine learning-based q-RASAR approach, Nanotoxicology, DOI: 10.1080/17435390.2023.2186280

Machine Learning classification

Machine Learning Classification v1.0

(Uploaded on April 09, 2023)

It includes (i) the Feature selection option; (ii) both Optimizer and Model developer

Manual_CSL.pdf

Presently all tools are restricted.

The manual is available here.

Reference: Arkaprava Banerjee & Kunal Roy (2023) Machine-learning-based similarity meets traditional QSAR: “q-RASAR” for the enhancement of the external predictivity and detection of prediction confidence outliers in an hERG toxicity dataset. Chem Intell Lab Syst, https://doi.org/10.1016/j.chemolab.2023.104829